English
Related papers

Related papers: Gradient-based Jailbreak Images for Multimodal Fus…

200 papers

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Yunhan Zhao , Xiang Zheng , Xingjun Ma

In recent years, despite significant advancements in adversarial attack research, the security challenges in cross-modal scenarios, such as the transferability of adversarial attacks between infrared, thermal, and RGB images, have been…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Yunpeng Gong , Qingyuan Zeng , Dejun Xu , Zhenzhong Wang , Min Jiang

Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Sensen Gao , Xiaojun Jia , Yihao Huang , Ranjie Duan , Jindong Gu , Yang Bai , Yang Liu , Qing Guo

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

Cryptography and Security · Computer Science 2025-10-27 Xingwei Zhong , Kar Wai Fok , Vrizlynn L. L. Thing

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to…

Machine Learning · Computer Science 2026-02-03 Kaiyuan Cui , Yige Li , Yutao Wu , Xingjun Ma , Sarah Erfani , Christopher Leckie , Hanxun Huang

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 MaungMaung AprilPyone , Hitoshi Kiya

Despite the advancements in training Large Language Models (LLMs) with alignment techniques to enhance the safety of generated content, these models remain susceptible to jailbreak, an adversarial attack method that exposes security…

Computation and Language · Computer Science 2024-12-17 Jiahui Li , Yongchang Hao , Haoyu Xu , Xing Wang , Yu Hong

Text-to-image models have rapidly evolved from casual creative tools to professional-grade systems, achieving unprecedented levels of image quality and realism. Yet, most models are trained to map short prompts into detailed images,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Eyal Gutflaish , Eliran Kachlon , Hezi Zisman , Tal Hacham , Nimrod Sarid , Alexander Visheratin , Saar Huberman , Gal Davidi , Guy Bukchin , Kfir Goldberg , Ron Mokady

Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or…

Cryptography and Security · Computer Science 2026-04-16 Jiecong Wang , Haoran Li , Hao Peng , Ziqian Zeng , Zihao Wang , Haohua Du , Zhengtao Yu

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Idan Schwartz , Vésteinn Snæbjarnarson , Hila Chefer , Ryan Cotterell , Serge Belongie , Lior Wolf , Sagie Benaim

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form text in images, such as paragraphs in slides or documents,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Alex Jinpeng Wang , Linjie Li , Zhengyuan Yang , Lijuan Wang , Min Li

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Tong Liu , Zhixin Lai , Jiawen Wang , Gengyuan Zhang , Shuo Chen , Philip Torr , Vera Demberg , Volker Tresp , Jindong Gu

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

Computation and Language · Computer Science 2026-01-09 Wenpeng Xing , Mohan Li , Chunqiang Hu , Haitao Xu , Ningyu Zhang , Bo Lin , Meng Han

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…

Cryptography and Security · Computer Science 2026-04-24 Rui Yang Tan , Yujia Hu , Roy Ka-Wei Lee

Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange methods which replace less informative tokens with inter-modal…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Ding Jia , Jianyuan Guo , Kai Han , Han Wu , Chao Zhang , Chang Xu , Xinghao Chen

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Computation and Language · Computer Science 2025-05-27 Binhao Ma , Hanqing Guo , Zhengping Jay Luo , Rui Duan

Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows, making them the focus in recent years. Despite their remarkable capability to generate…

Computation and Language · Computer Science 2025-06-04 Wenxuan Wang , Kuiyi Gao , Youliang Yuan , Jen-tse Huang , Qiuzhi Liu , Shuai Wang , Wenxiang Jiao , Zhaopeng Tu

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Zonghao Ying , Haowen Dai , Lianyu Hu , Zonglei Jing , Quanchen Zou , Yaodong Yang , Aishan Liu , Xianglong Liu

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while…

Computation and Language · Computer Science 2025-10-23 Yanhong Li , Zixuan Lan , Jiawei Zhou